Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 19509
    Prev
    Next
    INDEX
    Explanations

    Beginning of a narrative

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Также
    -0.10
     😀↵↵
    -0.10
    
↵↵
    -0.10
     ​↵↵
    -0.10
     //}↵↵
    -0.10
     ♥↵↵
    -0.09
     ||↵↵
    -0.09
     ??↵↵
    -0.09
     ^^↵↵
    -0.09
    тей
    -0.09
    POSITIVE LOGITS
     and
    0.10
     initiating
    0.09
    .setup
    0.09
     daunting
    0.09
     initiation
    0.08
     outset
    0.08
     starts
    0.08
     explicit
    0.08
     intending
    0.08
     gestart
    0.08
    Activations Density 0.071%

    No Known Activations